Chen Lai
Software Engineer at Facebook
Menlo Park, California, United States
Summary
🤩
Rockstar🎓
Top SchoolChen Lai is a software engineer with a decade of experience specializing in mobile and edge machine learning systems, currently developing PyTorch Edge and a lightweight mobile interpreter at Facebook in Menlo Park. He has driven practical production work for PyTorch mobile—building Android/iOS workflows, integrating the lite interpreter into demos, and contributing to the high-profile pytorch/pytorch and pytorch/tutorials repositories. His contributions span backend performance (XNNPACK), quantization tooling, and JIT/export utilities, reflecting both low-level optimization and developer-facing usability. Prior roles include research and engineering stints at UC Berkeley, NASA Ames, and UC San Diego, giving him a strong research-to-production background. Notably, he shipped the mobile interpreter included in PyTorch 1.9 and has applied ML skills to XR camera calibration and factory deployment for Oculus.
10 years of coding experience
2 years of employment as a software developer
University of California San Diego
English, Chinese
Github Skills (15)
neural-network10
xpack10
pytorch10
machine-learning10
ios10
android-development10
model-optimization9
python9
cprogramming-language9
c-language9
deep-learning9
tensor8
autograd8
git7
quantization7
Programming languages (7)
Github contributions (5)
pytorch/pytorch
Nov 2020 - Jan 2023
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Role in this project:
ML Engineer
ML EngineerContributions:432 reviews, 167 commits, 257 PRs in 2 years 2 months
Contributions summary:Chen primarily contributed to the PyTorch framework, focusing on the XNNPACK backend and PyTorch Edge functionalities. Their work involved refactoring and modifying the XNNPACK graph schema, including adding debug handles and updating node definitions. Additionally, they implemented fixes for setting the training attribute within the JIT module and added utilities for accessing buffers within exported programs, thereby demonstrating their work on extending and improving the performance and usability of PyTorch features. The user has also made modifications to improve the tooling for Quantization in PyTorch.
pythongpu-accelerationdeep-learninggpunumpy
pytorch/tutorials
Mar 2021 - Jan 2022
PyTorch tutorials.
Role in this project:Mobile Developer (Android/iOS)
Mobile Developer (Android/iOS)Contributions:12 reviews, 6 commits, 9 PRs in 10 months
Contributions summary:Chen primarily contributes to the implementation and integration of the lite interpreter within the PyTorch tutorials repository, focusing on mobile platforms. They are responsible for establishing the workflow for Android and iOS, including model preparation, library building, and application integration. Their work involves modifying existing Android and iOS demo applications to utilize the lite interpreter, including updating the model loading APIs and build configurations. The user's contributions also involve updating and integrating new versions of the PyTorch mobile interpreter and demonstrating its use with custom builds and tracing.
deep-learningpytorchpytorch-tutorials
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.